• 디지털융복합연구
• /
• 제18권12호
• /
• pp.97-103
• /
• 2020

제안한 시스템은 AI 체력측정 파트와 AI 체력관리 파트 2가지 부분이 연계성을 가지고 구성되어 있다. AI 체력측정 파트에서 딥러닝 기반의 포즈인식을 통해 체력측정에 대한 가이드와 측정값의 정확한 연산을 수행한다. 이 측정값을 기반으로 AI 체력관리 파트에서는 개인 맞춤형 운동프로그램을 설계해 전용 스마트 어플리케이션에 제공한다. 측정자세 가이드를 위해 웹캠을 통해 측정대상자의 자세를 촬영해 골격선을 추출한다. 다음으로 학습된 준비자세의 골격선과 추출된 골격선을 비교해 정상 유무를 판단하고, 정상자세 유지를 위한 음성안내를 실시한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1535-1538
• /
• 2004

In this paper, an Intelligent Bed Robot System (IBRS) is proposed, that is a special bed equipped with robot manipulator. To assist a patient using IBRS, pose and motion estimation process is fundamental. It is designed to help the elderly and the disabled for their independent life in bed without other assistants. For this purpose, we use the pressure sensor distributed mattress for detecting the change of motion on the bed. Using that data, we control the robot arm to move to the appropriate position and serve to the user. In addition, we can estimate the user's intention based on the change of pressure and use those data to control the robot arm guide.

• 로봇학회논문지
• /
• 제18권4호
• /
• pp.463-471
• /
• 2023

This paper proposes a method to estimate the level of interest shown by visitors towards a specific target, a guide robot, in spaces where a large number of visitors, such as exhibition halls and museums, can show interest in a specific subject. To accomplish this, we apply deep learning-based behavior recognition and object tracking techniques for multiple visitors, and based on this, we derive the behavior analysis and interest level of visitors. To implement this research, a personalized dataset tailored to the characteristics of exhibition hall and museum environments was created, and a deep learning model was constructed based on this. Four scenarios that visitors can exhibit were classified, and through this, prediction and experimental values were obtained, thus completing the validation for the interest estimation method proposed in this paper.

• 한국공작기계학회논문집
• /
• 제12권1호
• /
• pp.8-15
• /
• 2003

The cylindrical object such as a water pipe or an oil pipeline are widely used in the infrastructure. Those pipes should be inspected periodically by human or a robot. However, since there is no edge or vertex in the pipe, it is very difficult for the robot to navigate along the pipe. In this paper in order to guide the robot along the axis of the pipe, an algorithm which find the axis using the measured range data from the robot to the pipe wall is developed The algorithm is verified using both the simulated range data and the measured one.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2009년도 정보 및 제어 심포지움 논문집
• /
• pp.396-398
• /
• 2009

Scoliosis is a three-dimensional deformity caused by lateral curvature of the spine. The existing braces used to correct the posture were some drawbacks such as inconvenience, tightness as well as unfitness to wear. In this study, we devised a posture guidance system in order to monitor a posture continuously and lead to pose correctly and a new method fur measuring a Cobb's angle value in third dimension based on two 3-axis accelerometers. As a result, the correlation coefficients between desired and measured angles were and standard error between desired and measured angles were 0.99, 1.32(x-axis), 0.99 and 1.10(y-axis), respectively. The devised system showed good potential for the optimal posture guide and an early detection of scoliosis.

• 대한가정학회지
• /
• 제23권4호
• /
• pp.9-17
• /
• 1985

The pur[pose of this study is to investigate the research method and to provide a guide to the ways in which researcher, interested in costume history, can obtain in formation. There are comparison, induction, observation, awnalysis, experience and synthesis in method of science. Firstly, comparative research is to ascertain the accumulated evidence. Secondly, we can compare with historical phenomenon. A research intend to verify the hypothesis based upon the sources of information. It is an available method to investigate the costumes and adornments in the past. Whatever the approach, the researcher much discribe the facts objectively. Historical research has been approached in many warys in the field of costume. There are visual and documentary sources. Visual sources are paintings, sculptutre, frescoes, coins, potteries, medals, mosaics, wall paintings, stained glasses, seals, tapestries, illustrations, photographs, movies, and fashion dolls. Documentary sources are archives, letters, diaries, literature, wardrobe accounts, sumpturary laws, newspapers, and recollections.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2001년도 추계학술대회 논문집
• /
• pp.429-434
• /
• 2001

Rail crossings pose special safety concerns for modern railroad operation with faster trains. More than ninety percent of train operation-related accidents occurs on at-grade crossings. Surest countermeasure for this safety hazard is to eliminate at-grade crossings by constructing over/under pass or by closing them. These eliminations usually require substantial amount of investment and/or heavy public protest from those affected by them. Thorough and objective analysis are usually required, and valid accident prediction models are essential to the process. This paper developed an accident prediction model for Korean at-grade crossings. The model utilized many important factors such as guide personnel, highway traffic, train frequency, train sight distance, and number of tracks. Developed model was validated with actual accident data.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.231-233
• /
• 2007

In this paper we present a new visual approach for the robust bin-picking in a two-step concept for a vision driven automatic handling robot. The technology described here is based on two types of sensors: 3D laser scanner and CCD video camera. The geometry and pose(position and orientation) information of bin contents was reconstructed from the camera and laser sensor. these information can be employed to guide the robotic arm. A new thinning algorithm and constrained hough transform method is also explained in this paper. Consequently, the developed bin-picking demonstrate the successful operation with 3D hole object.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2023년도 제68차 하계학술대회논문집 31권2호
• /
• pp.355-356
• /
• 2023

K-POP의 가파른 성장세에 따라 댄스 콘텐츠 산업이 확산되는 추세이다. 최근 SNS의 보급이 증가하면서 자신의 댄스 영상을 촬영하고 공유하기도 한다. 그러나 초보자들은 자신의 동작이 어떻게 보이는지 평가하는 데 어려움을 겪어 춤동작을 습득하기 쉽지 않다. 본 논문에서는 MediaPipe를 활용하여 안무 영상과 사용자의 춤영상을 비교하고 올바르게 동작을 따라 하고 있는지 검출해 주는 시스템에 대해 기술한다. 본 시스템을 통해 사용자의 춤동작에 대한 피드백을 받을 수 있으며 초보자들도 정확한 춤동작을 연습할 수 있을 것으로 기대한다.

• Mycobiology
• /
• 제51권5호
• /
• pp.333-342
• /
• 2023

Phytophthora species, classified under Oomycota, cause significant damage to various crops and trees. The present study introduced Phytophthora species, P. nagaii and P. tentaculata, new to Korea, which pose notable risks to their respective host plants. Our research provided a comprehensive description of these species taking into account their cultural features, morphological characteristics, and molecular phylogenetic analysis using the internal transcribed spacer rDNA region and cytochrome c oxidase subunit mtDNA genes (cox1 and cox2) sequences. In addition, this study first evaluated the sensitivity of P. nagaii and P. tentaculata to five anti-oomycete fungicides, finding both species most responsive to picarbutrazox and P. tentaculata resistant to fluazinam. The data can guide targeted treatment strategies and offer insights into effective control methods. The findings expand our understanding of the diversity, distribution, and management of Phytophthora species in Korea.